Medical language model specialized in extracting cardiac knowledge

Hansle Gwon, Jiahn Seo, Seohyun Park, Young-Hak Kim, Tae Joon Jun · 2024

Read Medical language model specialized in extracting cardiac knowledge by Hansle Gwon, Jiahn Seo, Seohyun Park, Young-Hak Kim, Tae Joon Jun (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11585629.txt.

Description

General medical language models treat medicine as one field, but a cardiologist's language is its own dialect of terms, measures, and shorthand. Hansle Gwon and co-authors build a model fluent in that dialect in a 2024 study. Their work covers the full pipeline: gathering open data, training the model to pull heart knowledge from text, and testing it.

The aim is extraction, turning messy notes and papers into clean facts about hearts that other systems can use. A model steeped in one specialty's texts should miss less and misread less than a generalist. The team released their data sets openly so others can build on them. The study argues that the next gains in medical language tools will come specialty by specialty, not from ever-wider general models.

Catalog record

CREATORHansle Gwon, Jiahn Seo, Seohyun Park, Young-Hak Kim, Tae Joon Jun
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE38 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11585629

Browse the full library · About the Tower of Babel